Search results for: deep reinforcement learning

Authors: Eric Fang, Robert Chen, Ghim Song Chia, Bien Soo Tan

Abstract:

Objective and Rationale: Training of radiology residents hinges on practical, on-the-job training in all facets and modalities of diagnostic radiology. Although residency is structured to be comprehensive, clinical exposure depends on the case mix available locally and during the posting period. To supplement clinical training, there are several e-learning resources available to allow for greater exposure to radiological cases. The objective of this study was to survey residents and faculty on the usefulness of these e-learning resources. Methods: E-learning resources were shortlisted with input from radiology residents, Google search and online discussion groups, and screened by their purported focus. Twelve e-learning resources were found to meet the criteria. Both radiology residents and experienced radiology faculty were then surveyed electronically. The e-survey asked for ratings on breadth, depth, testing capability and user-friendliness for each resource, as well as for rankings for the top 3 resources. Statistical analysis was performed using SAS 9.4. Results: Seventeen residents and fifteen faculties completed an e-survey. Mean response rate was 54% ± 8% (Range: 14- 96%). Ratings and rankings were statistically identical between residents and faculty. On a 5-point rating scale, breadth was 3.68 ± 0.18, depth was 3.95 ± 0.14, testing capability was 2.64 ± 0.16 and user-friendliness was 3.39 ± 0.13. Top-ranked resources were STATdx (first), Radiopaedia (second) and Radiology Assistant (third). 9% of responders singled out R-ITI as potentially good but ‘prohibitively costly’. Statistically significant predictive factors for higher rankings are familiarity with the resource (p = 0.001) and user-friendliness (p = 0.006). Conclusion: A good e-learning system will complement on-the-job training with a broad case base, deep discussion and quality trainee evaluation. Based on our study on twelve e-learning resources, no single program fulfilled all requirements. The perception and use of radiology e-learning resources depended more on familiarity and user-friendliness than on content differences and testing capability.

Keywords: e-learning, medicine, radiology, survey

Procedia PDF Downloads 319

Authors: Joseph M. Rich, Vinay A. Duddalwar, Assad A. Oberai

Abstract:

Prostate adenocarcinoma is the most common cancer in males, with osseous metastases as the commonest site of metastatic prostate carcinoma (mPC). Treatment monitoring is based on the evaluation and characterization of lesions on multiple imaging studies, including Computed Tomography (CT). Monitoring of the osseous disease burden, including follow-up of lesions and identification and characterization of new lesions, is a laborious task for radiologists. Deep learning algorithms are increasingly used to perform tasks such as identification and segmentation for osseous metastatic disease and provide accurate information regarding metastatic burden. Here, nnUNet was used to produce a model which can segment CT scan images of prostate adenocarcinoma vertebral bone metastatic lesions. nnUNet is an open-source Python package that adds optimizations to deep learning-based UNet architecture but has not been extensively combined with transfer learning techniques due to the absence of a readily available functionality of this method. The IRB-approved study data set includes imaging studies from patients with mPC who were enrolled in clinical trials at the University of Southern California (USC) Health Science Campus and Los Angeles County (LAC)/USC medical center. Manual segmentation of metastatic lesions was completed by an expert radiologist Dr. Vinay Duddalwar (20+ years in radiology and oncologic imaging), to serve as ground truths for the automated segmentation. Despite nnUNet’s success on some medical segmentation tasks, it only produced an average Dice Similarity Coefficient (DSC) of 0.31 on the USC dataset. DSC results fell in a bimodal distribution, with most scores falling either over 0.66 (reasonably accurate) or at 0 (no lesion detected). Applying more aggressive data augmentation techniques dropped the DSC to 0.15, and reducing the number of epochs reduced the DSC to below 0.1. Datasets have been identified for transfer learning, which involve balancing between size and similarity of the dataset. Identified datasets include the Pancreas data from the Medical Segmentation Decathlon, Pelvic Reference Data, and CT volumes with multiple organ segmentations (CT-ORG). Some of the challenges of producing an accurate model from the USC dataset include small dataset size (115 images), 2D data (as nnUNet generally performs better on 3D data), and the limited amount of public data capturing annotated CT images of bone lesions. Optimizations and improvements will be made by applying transfer learning and generative methods, including incorporating generative adversarial networks and diffusion models in order to augment the dataset. Performance with different libraries, including MONAI and custom architectures with Pytorch, will be compared. In the future, molecular correlations will be tracked with radiologic features for the purpose of multimodal composite biomarker identification. Once validated, these models will be incorporated into evaluation workflows to optimize radiologist evaluation. Our work demonstrates the challenges of applying automated image segmentation to small medical datasets and lays a foundation for techniques to improve performance. As machine learning models become increasingly incorporated into the workflow of radiologists, these findings will help improve the speed and accuracy of vertebral metastatic lesions detection.

Keywords: deep learning, image segmentation, medicine, nnUNet, prostate carcinoma, radiomics

Procedia PDF Downloads 80

Authors: Aisha Iddrisu

Abstract:

The proliferation of cyberviolence in the wave of increased social media consumption calls for immediate attention both at the local and global levels. With over 4.70 billion social media users worldwide and 8.8 social media users in Ghana, various forms of violence have become the order of the day in most countries and communities. Cyber violence is defined as producing, retrieving, and sharing of hurtful or dangerous online content to cause emotional, psychological, or physical harm. The urgency and severity of cyber violence have led to the enactment of laws in various countries though lots still need to be done, especially in Ghana. In Ghana, studies on cyber violence have not been extensively dealt with. Existing studies concentrate only on one form or the other form of cyber violence, thus cybercrime and cyber bullying. Also, most studies in Africa have not explored cyber violence forms using empirical theories and the few that existed were qualitatively researched, whereas others examine the effect of cyber violence rather than examining why those who involve in it behave the way they behave. It is against this backdrop that this study aims to examine various cyber violence behaviour among social media users in Ghana by applying the theory of Self-control and Social control theory. This study is important for the following reasons. The outcome of this research will help at both national and international level of policymaking by adding to the knowledge of understanding cyberviolence and why people engage in various forms of cyberviolence. It will also help expose other ways by which such behaviours are enforced thereby serving as a guide in the enactment of the rightful rules and laws to curb such behaviours. It will add to literature on consequences of new media. This study seeks to confirm or reject to the following research hypotheses. H1 Social media usage has direct significant effect of cyberviolence behaviours. H2 Ineffective parental management has direct significant positive relation to Low self-control. H3 Low self-control has direct significant positive effect on cyber violence behaviours among social, H4 Differential association has significant positive effect on cyberviolence behaviour among social media users in Ghana. H5 Definitions have a significant positive effect on cyberviolence behaviour among social media users in Ghana. H6 Imitation has a significant positive effect on cyberviolence behaviour among social media users in Ghana. H7 Differential reinforcement has a significant positive effect on cyberviolence behaviour among social media users in Ghana. H8 Differential association has a significant positive effect on definitions. H9 Differential association has a significant positive effect on imitation. H10 Differential association has a significant positive effect on differential reinforcement. H11 Differential association has significant indirect positive effects on cyberviolence through the learning process.

Keywords: cyberviolence, social media users, self-control theory, social learning theory

Procedia PDF Downloads 60

Authors: Larisa Liamina, Vasily Lavrushin, Salvatore Inguaggiato

Abstract:

This study presents and summarizes the results of researching the isotopic signature of helium in the deep fluid eastern part of the Southern slope of the Greater Caucasus and the Lesser Caucasus (Azerbaijan and Armenia) for the period from 2010 to 2016. The results of isotope ratios of 3He/4He in 59 samples of the gas phase of geothermal fluids and mud volcanoes are presented. New data have been obtained not only on the isotopic ratios of helium, but also neon and argon. The R/Ra ratio was analyzed along the Ankara-Sevan ophiolite structure. The patterns of lateral variations of the 3He/4He ratio of different geological structural elements of the studied region are revealed.

Keywords: isotopes helium, deep fluids, tectonic structures, Caucasus

Procedia PDF Downloads 22

Authors: Farouk Lawan Gambo

Abstract:

Data compression shrinks files into fewer bits then their original presentation. It has more advantage on internet because the smaller a file, the faster it can be transferred but learning most of the concepts in data compression are abstract in nature therefore making them difficult to digest by some students (Engineers in particular). To determine the best approach toward learning data compression technique, this paper first study the learning preference of engineering students who tend to have strong active, sensing, visual and sequential learning preferences, the paper also study the advantage that mobility of learning have experienced; Learning at the point of interest, efficiency, connection, and many more. A survey is carried out with some reasonable number of students, through random sampling to see whether considering the learning preference and advantages in mobility of learning will give a promising improvement over the traditional way of learning. Evidence from data analysis using Ms-Excel as a point of concern for error-free findings shows that there is significance different in the students after using learning content provided on smart phone, also the result of the findings presented in, bar charts and pie charts interpret that mobile learning has to be promising feature of learning.

Keywords: data analysis, compression techniques, learning content, traditional learning approach

Procedia PDF Downloads 334

Authors: Jean-Francois Rajotte, Martin Sotir, Frank Gouineau

Abstract:

The installation and management of traffic monitoring devices can be costly from both a financial and resource point of view. It is therefore important to take advantage of in-place infrastructures to extract the most information. Here we show how low-quality urban road traffic images from cameras already available in many cities (such as Montreal, Vancouver, and Toronto) can be used to estimate traffic flow. To this end, we use a pre-trained neural network, developed for object detection, to count vehicles within images. We then compare the results with human annotations gathered through crowdsourcing campaigns. We use this comparison to assess performance and calibrate the neural network annotations. As a use case, we consider six months of continuous monitoring over hundreds of cameras installed in the city of Montreal. We compare the results with city-provided manual traffic counting performed in similar conditions at the same location. The good performance of our system allows us to consider applications which can monitor the traffic conditions in near real-time, making the counting usable for traffic-related services. Furthermore, the resulting annotations pave the way for building a historical vehicle counting dataset to be used for analysing the impact of road traffic on many city-related issues, such as urban planning, security, and pollution.

Keywords: traffic monitoring, deep learning, image annotation, vehicles, roads, artificial intelligence, real-time systems

Procedia PDF Downloads 179

Authors: Dongping Fang, Lian Duan, Xiaojing Yuan, Mike Xu, Allyn Klunder, Kevin Tan, Suiting Cao, Yeqing Ji

Abstract:

Accurate prediction of a medical condition with straight clinical evidence is a long-sought topic in the medical management and health insurance field. Although great progress has been made with machine learning algorithms, the medical community is still, to a certain degree, suspicious about the model's accuracy and interpretability. This paper presents an innovative hierarchical attention deep learning model to achieve good prediction and clear interpretability that can be easily understood by medical professionals. This deep learning model uses a hierarchical attention structure that matches naturally with the medical history data structure and reflects the member’s encounter (date of service) sequence. The model attention structure consists of 3 levels: (1) attention on the medical code types (diagnosis codes, procedure codes, lab test results, and prescription drugs), (2) attention on the sequential medical encounters within a type, (3) attention on the medical codes within an encounter and type. This model is applied to predict the occurrence of stage 3 chronic kidney disease (CKD3), using three years’ medical history of Medicare Advantage (MA) members from a top health insurance company. The model takes members’ medical events, both claims and electronic medical record (EMR) data, as input, makes a prediction of CKD3 and calculates the contribution from individual events to the predicted outcome. The model outcome can be easily explained with the clinical evidence identified by the model algorithm. Here are examples: Member A had 36 medical encounters in the past three years: multiple office visits, lab tests and medications. The model predicts member A has a high risk of CKD3 with the following well-contributed clinical events - multiple high ‘Creatinine in Serum or Plasma’ tests and multiple low kidneys functioning ‘Glomerular filtration rate’ tests. Among the abnormal lab tests, more recent results contributed more to the prediction. The model also indicates regular office visits, no abnormal findings of medical examinations, and taking proper medications decreased the CKD3 risk. Member B had 104 medical encounters in the past 3 years and was predicted to have a low risk of CKD3, because the model didn’t identify diagnoses, procedures, or medications related to kidney disease, and many lab test results, including ‘Glomerular filtration rate’ were within the normal range. The model accurately predicts members A and B and provides interpretable clinical evidence that is validated by clinicians. Without extra effort, the interpretation is generated directly from the model and presented together with the occurrence date. Our model uses the medical data in its most raw format without any further data aggregation, transformation, or mapping. This greatly simplifies the data preparation process, mitigates the chance for error and eliminates post-modeling work needed for traditional model explanation. To our knowledge, this is the first paper on an interpretable deep-learning model using a 3-level attention structure, sourcing both EMR and claim data, including all 4 types of medical data, on the entire Medicare population of a big insurance company, and more importantly, directly generating model interpretation to support user decision. In the future, we plan to enrich the model input by adding patients’ demographics and information from free-texted physician notes.

Keywords: deep learning, interpretability, attention, big data, medical conditions

Procedia PDF Downloads 79

Authors: Li Hui, Riyadh Hindi

Abstract:

In the United States, bridge construction often employs overhang brackets to support the deck overhang, the weight of fresh concrete, and loads from construction equipment. This approach, however, can lead to significant torsional moments on the exterior girders, potentially causing excessive girder rotation. Such rotations can result in various safety and maintenance issues, including thinning of the deck, reduced concrete cover, and cracking during service. Traditionally, these issues are addressed by installing temporary lateral bracing systems and conducting comprehensive torsional analysis through detailed finite element analysis for the construction of bridge deck overhang. However, this process is often intricate and time-intensive, with the spacing between temporary lateral bracing systems usually relying on the field engineers’ expertise. In this study, a deep neural network model is introduced to limit exterior girder rotation during bridge deck construction. The model predicts the optimal spacing between temporary bracing systems. To train this model, over 10,000 finite element models were generated in SAP2000, incorporating varying parameters such as girder dimensions, span length, and types and spacing of lateral bracing systems. The findings demonstrate that the deep neural network provides an effective and efficient alternative for limiting the exterior girder rotation for bridge deck construction. By reducing dependence on extensive finite element analyses, this approach stands out as a significant advancement in improving safety and maintenance effectiveness in the construction of bridge decks.

Keywords: bridge deck construction, exterior girder rotation, deep learning, finite element analysis

Procedia PDF Downloads 41

Authors: Yaolin Tian, Shanxiong Chen, Fujia Zhao, Xiaoyu Lin, Hailing Xiong

Abstract:

Ancient books are significant culture inheritors and their background textures convey the potential history information. However, multi-style texture recovery of ancient books has received little attention. Restricted by insufficient ancient textures and complex handling process, the generation of ancient textures confronts with new challenges. For instance, training without sufficient data usually brings about overfitting or mode collapse, so some of the outputs are prone to be fake. Recently, image generation and style transfer based on deep learning are widely applied in computer vision. Breakthroughs within the field make it possible to conduct research upon multi-style texture recovery of ancient books. Under the circumstances, we proposed a network of layout analysis and image fusion system. Firstly, we trained models by using Deep Convolution Generative against Networks (DCGAN) to synthesize multi-style ancient textures; then, we analyzed layouts based on the Position Rearrangement (PR) algorithm that we proposed to adjust the layout structure of foreground content; at last, we realized our goal by fusing rearranged foreground texts and generated background. In experiments, diversified samples such as ancient Yi, Jurchen, Seal were selected as our training sets. Then, the performances of different fine-turning models were gradually improved by adjusting DCGAN model in parameters as well as structures. In order to evaluate the results scientifically, cross entropy loss function and Fréchet Inception Distance (FID) are selected to be our assessment criteria. Eventually, we got model M8 with lowest FID score. Compared with DCGAN model proposed by Radford at el., the FID score of M8 improved by 19.26%, enhancing the quality of the synthetic images profoundly.

Keywords: deep learning, image fusion, image generation, layout analysis

Procedia PDF Downloads 138

Authors: Muhamamd Shahid Farooq, Maazan Zafar, Rizawana Akhtar

Abstract:

E-learning technologies are the blessings of advancements in science and technology. These facilitate the learners to get information at any place and any time by improving their self-confidence, self-efficacy and effectiveness in teaching learning process. E-learning provides an individualized learning experience for learners and remove barriers faced by students during new and creative ways of gaining information. It provides a wide range of facilities to enable the teachers and students for effective and purposeful learning. This study was conducted to explore the attitudes of university students and teachers towards e-learning working in a metropolitan university of Pakistan. The personal, institutional and technological characteristics of the teachers and students of higher education institution effect the adoption of e-learning. For this descriptive study 449 students and 35 university teachers were surveyed by using a Likert scale type questionnaire consisting of 52 statements relating to six factors "perceived usefulness, intention to adopt e-learning, ease of e-learning use, availability resources, e-learning stressors, and pressure to use e-learning". Data were analyzed by making comparisons on the basis of different demographic factors. The findings of the study show that both type of respondents have positive attitude towards e-learning. However, the male and female respondents differ in their opinion for e-learning implementation.

Keywords: e-learning, ICT, e-sources of learning, questionnaire

Procedia PDF Downloads 514

Authors: Boris Kolev, Matt Kokan, Mohammad Deriszadeh, Farshid Bateni

Abstract:

Due to the increasing demand for real estate and the need for efficient land utilization in Greater Vancouver, developers have been increasingly considering the construction of high-rise structures with multiple below-grade parking. The temporary excavations required to allow for the construction of underground levels have recently reached up to 40 meters in depth. One of the challenges with deep excavations is the prediction of wall displacements and ground settlements due to their effect on the integrity of City utilities, infrastructure, and adjacent buildings. A large database of survey monitoring data has been collected for deep excavations in various soil conditions and shoring systems. The majority of the data collected is for tie-back anchors and shotcrete lagging systems. The data were categorized, analyzed and the results were evaluated to find a relationship between the most dominant parameters controlling the displacement, such as depth of excavation, soil properties, and the tie-back anchor loading and arrangement. For a select number of deep excavations, finite element modeling was considered for analyses. The lateral displacements from the simulation results were compared to the recorded survey monitoring data. The study concludes with a discussion and comparison of the available empirical and numerical modeling methodologies for evaluating lateral displacements in deep excavations.

Keywords: deep excavations, lateral displacements, numerical modeling, shoring walls, tieback anchors

Procedia PDF Downloads 163

Authors: Reggie Chandra

Abstract:

Trafficaccidents and traffic signal optimization are correlated. However, 70-90% of the traffic signals across the USA are not synchronized. The reason behind that is insufficient resources to create and implement timing plans. In this work, we will discuss the use of a breakthrough Artificial Intelligence (AI) technology to optimize traffic flow and collect 24/7/365 accurate traffic data using a vehicle detection system. We will discuss what are recent advances in Artificial Intelligence technology, how does AI work in vehicles, pedestrians, and bike data collection, creating timing plans, and what is the best workflow for that. Apart from that, this paper will showcase how Artificial Intelligence makes signal timing affordable. We will introduce a technology that uses Convolutional Neural Networks (CNN) and deep learning algorithms to detect, collect data, develop timing plans and deploy them in the field. Convolutional Neural Networks are a class of deep learning networks inspired by the biological processes in the visual cortex. A neural net is modeled after the human brain. It consists of millions of densely connected processing nodes. It is a form of machine learning where the neural net learns to recognize vehicles through training - which is called Deep Learning. The well-trained algorithm overcomes most of the issues faced by other detection methods and provides nearly 100% traffic data accuracy. Through this continuous learning-based method, we can constantly update traffic patterns, generate an unlimited number of timing plans and thus improve vehicle flow. Convolutional Neural Networks not only outperform other detection algorithms but also, in cases such as classifying objects into fine-grained categories, outperform humans. Safety is of primary importance to traffic professionals, but they don't have the studies or data to support their decisions. Currently, one-third of transportation agencies do not collect pedestrian and bike data. We will discuss how the use of Artificial Intelligence for data collection can help reduce pedestrian fatalities and enhance the safety of all vulnerable road users. Moreover, it provides traffic engineers with tools that allow them to unleash their potential, instead of dealing with constant complaints, a snapshot of limited handpicked data, dealing with multiple systems requiring additional work for adaptation. The methodologies used and proposed in the research contain a camera model identification method based on deep Convolutional Neural Networks. The proposed application was evaluated on our data sets acquired through a variety of daily real-world road conditions and compared with the performance of the commonly used methods requiring data collection by counting, evaluating, and adapting it, and running it through well-established algorithms, and then deploying it to the field. This work explores themes such as how technologies powered by Artificial Intelligence can benefit your community and how to translate the complex and often overwhelming benefits into a language accessible to elected officials, community leaders, and the public. Exploring such topics empowers citizens with insider knowledge about the potential of better traffic technology to save lives and improve communities. The synergies that Artificial Intelligence brings to traffic signal control and data collection are unsurpassed.

Keywords: artificial intelligence, convolutional neural networks, data collection, signal control, traffic signal

Procedia PDF Downloads 142

Authors: Tahar Alimi, Rahma Boujebane, Wiem Derouich, Lamia Hadrich Belguith

Abstract:

Machine translation task of low-resourced languages such as Arabic is a challenging task. Despite the appearance of sophisticated models based on the latest deep learning techniques, namely the transfer learning, and transformers, all models prove incapable of carrying out an acceptable translation, which includes Arabic Dialects (AD), because they do not have official status. In this paper, we present a machine translation model designed to translate Arabic multidialectal content into Modern Standard Arabic (MSA), leveraging both new and existing parallel resources. The latter achieved the best results for both Levantine and Maghrebi dialects with a BLEU score of 64.99.

Keywords: Arabic translation, dialect translation, fine-tune, MSA translation, transformer, translation

Procedia PDF Downloads 32

Authors: O. Bourkoukou, Essaid El Bachari

Abstract:

The group composing is one of the key issue in collaborative learning to achieve a positive educational experience. The goal of this work is to propose for teachers and tutors a method to create effective collaborative learning groups in e-learning environment based on the learner profile. For this purpose, a new function was defined to rate implicitly learning objects used by the learner during his learning experience. This paper describes the proposed algorithm to build an adequate collaborative learning group. In order to verify the performance of the proposed algorithm, several experiments were conducted in real data set in virtual environment. Results show the effectiveness of the method for which it appears that the proposed approach may be promising to produce better outcomes.

Keywords: building groups, collaborative learning, e-learning, learning objects

Procedia PDF Downloads 282

Authors: Ola Hall, Ibrahim Wahab, Thorsteinn Rognvaldsson, Mattias Ohlsson

Abstract:

The subfield of poverty and welfare estimation that applies machine learning tools and methods on satellite imagery is a nascent but rapidly growing one. This is in part driven by the sustainable development goal, whose overarching principle is that no region is left behind. Among other things, this requires that welfare levels can be accurately and rapidly estimated at different spatial scales and resolutions. Conventional tools of household surveys and interviews do not suffice in this regard. While they are useful for gaining a longitudinal understanding of the welfare levels of populations, they do not offer adequate spatial coverage for the accuracy that is needed, nor are their implementation sufficiently swift to gain an accurate insight into people and places. It is this void that satellite imagery fills. Previously, this was near-impossible to implement due to the sheer volume of data that needed processing. Recent advances in machine learning, especially the deep learning subtype, such as deep neural networks, have made this a rapidly growing area of scholarship. Despite their unprecedented levels of performance, such models lack transparency and explainability and thus have seen limited downstream applications as humans generally are apprehensive of techniques that are not inherently interpretable and trustworthy. While several studies have demonstrated the superhuman performance of AI models, none has directly compared the performance of such models and human readers in the domain of poverty studies. In the present study, we directly compare the performance of human readers and a DL model using different resolutions of satellite imagery to estimate the welfare levels of demographic and health survey clusters in Tanzania, using the wealth quintile ratings from the same survey as the ground truth data. The cluster-level imagery covers all 608 cluster locations, of which 428 were classified as rural. The imagery for the human readers was sourced from the Google Maps Platform at an ultra-high resolution of 0.6m per pixel at zoom level 18, while that of the machine learning model was sourced from the comparatively lower resolution Sentinel-2 10m per pixel data for the same cluster locations. Rank correlation coefficients of between 0.31 and 0.32 achieved by the human readers were much lower when compared to those attained by the machine learning model – 0.69-0.79. This superhuman performance by the model is even more significant given that it was trained on the relatively lower 10-meter resolution satellite data while the human readers estimated welfare levels from the higher 0.6m spatial resolution data from which key markers of poverty and slums – roofing and road quality – are discernible. It is important to note, however, that the human readers did not receive any training before ratings, and had this been done, their performance might have improved. The stellar performance of the model also comes with the inevitable shortfall relating to limited transparency and explainability. The findings have significant implications for attaining the objective of the current frontier of deep learning models in this domain of scholarship – eXplainable Artificial Intelligence through a collaborative rather than a comparative framework.

Keywords: poverty prediction, satellite imagery, human readers, machine learning, Tanzania

Procedia PDF Downloads 83

Authors: Julian Thrash, Douglas Folk, Michael Ciracy, Audrey C. Tseng, Kristen M. Stromsodt, Amber Younggren, Christopher Maciolek

Abstract:

The cardiopulmonary system is comprised of the heart, lungs, and many dynamic feedback mechanisms that control its function based on a multitude of variables. The next generation of cardiopulmonary medical devices will involve adaptive control and smart pacing techniques. However, testing these smart devices on living systems may be unethical and exceedingly expensive. As a solution, a comprehensive computational model of the cardiopulmonary system was implemented in Simulink. The model contains over 240 state variables and over 100 equations previously described in a series of published articles. Simulink was chosen because of its ease of introducing machine learning elements. Initial results indicate that physiologically correct waveforms of pressures and volumes were obtained in the simulation. With the development of a comprehensive computational model, we hope to pioneer the future of predictive medicine by applying our research towards the initial stages of smart devices. After validation, we will introduce and train reinforcement learning agents using the cardiopulmonary model to assist in adaptive control system design. With our cardiopulmonary model, we will accelerate the design and testing of smart and adaptive medical devices to better serve those with cardiovascular disease.

Keywords: adaptive control, cardiopulmonary, computational model, machine learning, predictive medicine

Procedia PDF Downloads 156

Authors: Sulaiman Almutairy, Trevor Davies, Yota Dimitriadi

Abstract:

This paper presents study investigating how to understand better the psychological readiness for mobile learning (m-learning) among Saudi students, while also evaluating m-learning in Saudi Arabia-a topic that has not yet received adequate attention from researchers. Data was acquired through a questionnaire administered to 131 Saudi students at UK universities, in July 2013. The study confirmed that students are confident using mobile devices in their daily lives and that they would welcome more opportunities for mobile learning. The findings indicated that Saudi higher education students are highly familiar with, and are psychologically ready for, m-learning.

Keywords: m-learning, mobile technologies, psychological readiness, higher education

Procedia PDF Downloads 502

Authors: Sholeh Motaghian, Pekka Toivanen, Keiji Haataja

Abstract:

The swift expansion of the transportation industry and its associated emissions have captured the focus of policymakers who are dedicated to upholding ecological sustainability. As a result, understanding the key contributors to transportation emissions is of utmost significance. Amidst the escalating transportation emissions, the significance of electric vehicles cannot be overstated. Electric vehicles play a critical role in steering us towards a low-carbon economy and a sustainable ecological setting. The effective integration of electric vehicles hinges on the development of energy consumption models capable of accurately and efficiently predicting energy usage. Enhancing the energy efficiency of electric vehicles will play a pivotal role in reducing driver concerns and establishing a vital framework for the efficient operation, planning, and management of charging infrastructure. In this article, the works done in this field are reviewed, and the advantages and disadvantages of each are stated.

Keywords: deep learning, electrical vehicle, energy consumption, machine learning, smart grid

Procedia PDF Downloads 58

Authors: Chryssi Vitsilaki, Apostolos Kostas, Ilias Efthymiou

Abstract:

This paper presents selected best practices on online learning and teaching derived from a novel and innovating Lifelong Learning program through e-Learning, which has during the last five years been set up at the University of the Aegean in Greece. The university, capitalizing on an award-winning, decade-long experience in e-learning and blended learning in undergraduate and postgraduate studies, recently expanded into continuous education and vocational training programs in various cutting-edge fields. So, in this article we present: (a) the academic structure/infrastructure which has been developed for the administrative, organizational and educational support of the e-Learning process, including training the trainers, (b) the mode of design and implementation based on a sound pedagogical framework of open and distance education, and (c) the key results of the assessment of the e-learning process by the participants, as they are used to feedback on continuous organizational and teaching improvement and quality control.

Keywords: distance education, e-learning, life-long programs, synchronous/asynchronous learning

Procedia PDF Downloads 315

Authors: S. Bahadır Yüksel, Alptuğ Ünal

Abstract:

The composite shear walls (CSW) with steel encased profiles can be used as lateral-load resisting systems for buildings that require considerable large lateral-load capacity. The aim of this work is to propose the experimental work conducted on CSW having L section folded plate (L shape steel made-up sections) as longitudinal reinforcement in boundary regions. The study in this paper present the experimental test conducted on CSW having L section folded plate as longitudinal reinforcement in boundary regions. The tested 1/3 geometric scaled CSW has aspect ratio of 3.2. L-shape structural steel materials with 2L-19x57x7mm dimensions were placed in shear wall boundary zones. The seismic behavior of CSW test specimen was investigated by evaluating and interpreting the hysteresis curves, envelope curves, rigidity and consumed energy graphs of this tested element. In addition to this, the experimental results, deformation and cracking patterns were evaluated, interpreted and suggestions of the design recommendations were proposed.

Keywords: shear wall, composite shear wall, boundary reinforcement, earthquake resistant structural design, L section

Procedia PDF Downloads 310

Authors: Pitigalage Chamath Chandira Peiris

Abstract:

A widely researched domain in the field of image processing in recent times has been single image super-resolution, which tries to restore a high-resolution image from a single low-resolution image. Many more single image super-resolution efforts have been completed utilizing equally traditional and deep learning methodologies, as well as a variety of other methodologies. Deep learning-based super-resolution methods, in particular, have received significant interest. As of now, the most advanced image restoration approaches are based on convolutional neural networks; nevertheless, only a few efforts have been performed using Transformers, which have demonstrated excellent performance on high-level vision tasks. The effectiveness of CNN-based algorithms in image super-resolution has been impressive. However, these methods cannot completely capture the non-local features of the data. Enhancer is a simple yet powerful Transformer-based approach for enhancing the resolution of images. A method for single image super-resolution was developed in this study, which utilized an efficient and effective transformer design. This proposed architecture makes use of a locally enhanced window transformer block to alleviate the enormous computational load associated with non-overlapping window-based self-attention. Additionally, it incorporates depth-wise convolution in the feed-forward network to enhance its ability to capture local context. This study is assessed by comparing the results obtained for popular datasets to those obtained by other techniques in the domain.

Keywords: single image super resolution, computer vision, vision transformers, image restoration

Procedia PDF Downloads 89

Authors: Neha Singh, Shristi Singh

Abstract:

Accidents involving motor vehicles are more likely to cause serious injuries and fatalities. It also has a host of other perpetual issues, such as the regular loss of life and goods in accidents. To solve these issues, appropriate measures must be implemented, such as establishing an autonomous incident detection system that makes use of machine learning and artificial intelligence. In order to reduce traffic accidents, this article examines the overview of artificial intelligence and machine learning in autonomous event detection systems. The paper explores the major issues, prospective solutions, and use of artificial intelligence and machine learning in road transportation systems for minimising traffic accidents. There is a lot of discussion on additional, fresh, and developing approaches that less frequent accidents in the transportation industry. The study structured the following subtopics specifically: traffic management using machine learning and artificial intelligence and an incident detector with these two technologies. The internet of vehicles and vehicle ad hoc networks, as well as the use of wireless communication technologies like 5G wireless networks and the use of machine learning and artificial intelligence for the planning of road transportation systems, are elaborated. In addition, safety is the primary concern of road transportation. Route optimization, cargo volume forecasting, predictive fleet maintenance, real-time vehicle tracking, and traffic management, according to the review's key conclusions, are essential for ensuring the safety of road transportation networks. In addition to highlighting research trends, unanswered problems, and key research conclusions, the study also discusses the difficulties in applying artificial intelligence to road transport systems. Planning and managing the road transportation system might use the work as a resource.

Keywords: artificial intelligence, machine learning, incident detector, road transport systems, traffic management, automatic incident detection, deep learning

Procedia PDF Downloads 83

Authors: Zhou Hong, Gu Xiao-Qing, Lıu Hong-Jiao, Leng Jing

Abstract:

Seamless learning is becoming a research hotspot in recent years, and the emerging of micro-lectures, flipped classroom has strengthened the development of seamless learning. Based on the characteristics of the seamless learning across time and space and the course structure of the flipped classroom, and the theories of language learning, we put forward the language learning model which can support ‘seamless flipped’ environment (abbreviated as ‘S-F’). Meanwhile, the characteristics of the ‘S-F’ learning environment, the corresponding framework construction and the activity design of diversified corpora were introduced. Moreover, a language learning app named ‘Daily Speaking’ was developed to facilitate the practice of the language learning model in ‘S-F’ environment. In virtue of the learning case of Shanghai language, the rationality and feasibility of this framework were examined, expecting to provide a reference for the design of ‘S-F’ learning in different situations.

Keywords: seamless learning, flipped classroom, seamless-flipped environment, language learning model

Procedia PDF Downloads 169

Authors: S. A. Naeini, H. R. Rahmani, M. Hossein Zade

Abstract:

Many classical bearing capacity theories assume that the natural soil's layers are homogenous for determining the bearing capacity of the soil. But, in many practical projects, we encounter multi-layer soils. Geosynthetic as reinforcement materials have been extensively used in the construction of various structures. In this paper, numerical analysis of the Plate Load Test (PLT) using of ABAQUS software in double-layered soils with different thicknesses of sandy and gravelly layers reinforced with geogrid was considered. The PLT is one of the common filed methods to calculate parameters such as soil bearing capacity, the evaluation of the compressibility and the determination of the Subgrade Reaction module. In fact, the influence of the geogrid layers on the bearing capacity of the layered soils is investigated. Finally, the most appropriate mode for the distance and number of reinforcement layers is determined. Results show that using three layers of geogrid with a distance of 0.3 times the width of the loading plate has the highest efficiency in bearing capacity of double-layer (sand and gravel) soils. Also, the significant increase in bearing capacity between unreinforced and reinforced soil with three layers of geogrid is caused by the condition that the upper layer (gravel) thickness is equal to the loading plate width.

Keywords: bearing capacity, reinforcement, geogrid, plate load test, layered soils

Procedia PDF Downloads 157

Authors: Bikis Muhammed, Sehra Sedigh Sarvestani, Ali R. Hurson, Lasanthi Gamage

Abstract:

Vehicular traffic events have overly complex spatial correlations and temporal interdependencies and are also influenced by environmental events such as weather conditions. To capture these spatial and temporal interdependencies and make more realistic vehicular traffic predictions, graph neural networks (GNN) based traffic prediction models have been extensively utilized due to their capability of capturing non-Euclidean spatial correlation very effectively. However, most of the already existing GNN-based traffic prediction models have some limitations during learning complex and dynamic spatial and temporal patterns due to the following missing factors. First, most GNN-based traffic prediction models have used static distance or sometimes haversine distance mechanisms between spatially separated traffic observations to estimate spatial correlation. Secondly, most GNN-based traffic prediction models have not incorporated environmental events that have a major impact on the normal traffic states. Finally, most of the GNN-based models did not use an attention mechanism to focus on only important traffic observations. The objective of this paper is to study and make real-time vehicular traffic predictions while incorporating the effect of weather conditions. To fill the previously mentioned gaps, our prediction model uses a real-time driving distance between sensors to build a distance matrix or spatial adjacency matrix and capture spatial correlation. In addition, our prediction model considers the effect of six types of weather conditions and has an attention mechanism in both spatial and temporal data aggregation. Our prediction model efficiently captures the spatial and temporal correlation between traffic events, and it relies on the graph attention network (GAT) and Bidirectional bidirectional long short-term memory (Bi-LSTM) plus attention layers and is called GAT-BILSTMA.

Keywords: deep learning, real time prediction, GAT, Bi-LSTM, attention

Procedia PDF Downloads 56

Authors: Bindhu Lal, Karnika Kochal

Abstract:

Clayey soil contains clay minerals with traces of metal oxides and organic matter, which exhibits properties like low drainage, high plasticity, and shrinkage. To overcome these issues, various soil reinforcement techniques are used to elevate the stiffness, water tightness, and bearing capacity of the soil. Such techniques include cementation, bituminization, freezing, fiber inclusion, geo-synthetics, nailing, etc. Reinforcement of soil with fibers has been a cost-effective solution to soil improvement problems. An experimental study was undertaken involving the inclusion of cotton waste fibers in clayey soil as reinforcement with different fiber contents (1%, 1.5%, 2%, and 2.5% by weight) and analyzing its effects on the unconfined compressive strength of the soil. Two categories of soil were taken, comprising of natural clay and clay mixed with 5% sodium bentonite by weight. The soil specimens were subjected to proctor compaction and unconfined compression tests. The validated outcome shows that fiber inclusion has a strikingly positive impact on the compressive strength and axial strain at failure of the soil. Based on the commendatory results procured, compressive strength was found to be directly proportional to the fiber content, with the effect being more pronounced at lower water content.

Keywords: bentonite clay, clay, cotton fibers, unconfined compressive strength

Procedia PDF Downloads 157

Authors: Mohammed Abu Shquier

Abstract:

This paper introduces a word segmentation method using the novel BP-LSTM-CRF architecture for processing semantic output training. The objective of web morphological analysis tools is to link a formal morpho-syntactic description to a lemma, along with morpho-syntactic information, a vocalized form, a vocalized analysis with morpho-syntactic information, and a list of paradigms. A key objective is to continuously enhance the proposed system through an inductive learning approach that considers semantic influences. The system is currently under construction and development based on data-driven learning. To evaluate the tool, an experiment on homograph analysis was conducted. The tool also encompasses the assumption of deep binary segmentation hypotheses, the arbitrary choice of trigram or n-gram continuation probabilities, language limitations, and morphology for both Modern Standard Arabic (MSA) and Dialectal Arabic (DA), which provide justification for updating this system. Most Arabic word analysis systems are based on the phonotactic morpho-syntactic analysis of a word transmitted using lexical rules, which are mainly used in MENA language technology tools, without taking into account contextual or semantic morphological implications. Therefore, it is necessary to have an automatic analysis tool taking into account the word sense and not only the morpho-syntactic category. Moreover, they are also based on statistical/stochastic models. These stochastic models, such as HMMs, have shown their effectiveness in different NLP applications: part-of-speech tagging, machine translation, speech recognition, etc. As an extension, we focus on language modeling using Recurrent Neural Network (RNN); given that morphological analysis coverage was very low in dialectal Arabic, it is significantly important to investigate deeply how the dialect data influence the accuracy of these approaches by developing dialectal morphological processing tools to show that dialectal variability can support to improve analysis.

Keywords: NLP, DL, ML, analyser, MSA, RNN, CNN

Procedia PDF Downloads 22

Authors: Erick C. Valverde, Wansu Lim

Abstract:

Facial emotion recognition (FER) system has been recently developed for more advanced computer vision applications. The ability to identify human emotions would enable smart healthcare facility to diagnose mental health illnesses (e.g., depression and stress) as well as better human social interactions with smart technologies. The FER system involves two steps: 1) face detection task and 2) facial emotion recognition task. It classifies the human expression in various categories such as angry, disgust, fear, happy, sad, surprise, and neutral. This system requires intensive research to address issues with human diversity, various unique human expressions, and variety of human facial features due to age differences. These issues generally affect the ability of the FER system to detect human emotions with high accuracy. Early stage of FER systems used simple supervised classification task algorithms like K-nearest neighbors (KNN) and artificial neural networks (ANN). These conventional FER systems have issues with low accuracy due to its inefficiency to extract significant features of several human emotions. To increase the accuracy of FER systems, deep learning (DL)-based methods, like convolutional neural networks (CNN), are proposed. These methods can find more complex features in the human face by means of the deeper connections within its architectures. However, the inference speed and computational costs of a DL-based FER system is often disregarded in exchange for higher accuracy results. To cope with this drawback, an optimized DL-based FER system is proposed in this study.An extreme version of Inception V3, known as Xception model, is leveraged by applying different network optimization methods. Specifically, network pruning and quantization are used to enable lower computational costs and reduce memory usage, respectively. To support low resource requirements, a 68-landmark face detector from Dlib is used in the early step of the FER system.Furthermore, a DL compiler is utilized to incorporate advanced optimization techniques to the Xception model to improve the inference speed of the FER system. In comparison to VGG-Net and ResNet50, the proposed optimized DL-based FER system experimentally demonstrates the objectives of the network optimization methods used. As a result, the proposed approach can be used to create an efficient and real-time FER system.

Keywords: deep learning, face detection, facial emotion recognition, network optimization methods

Procedia PDF Downloads 102

Authors: Albin Wallace

Abstract:

This paper examines the use of social learning platforms in conjunction with the emergent pedagogy of the ‘flipped classroom’. In particular the attributes of the social learning platform “Edmodo” is considered alongside the changes in the way in which online learning environments are being implemented, especially within British education. Some observations are made regarding the use and usefulness of these platforms along with a consideration of the increasingly decentralized nature of education in the United Kingdom.

Keywords: education, Edmodo, Internet, learning platforms

Procedia PDF Downloads 526

Authors: Mohamed Haneef, Shanawaz Patil, Syed Zameer, Mohammed Mohsin Ali

Abstract:

The emerging technologies and trends of present generation requires downsizing the unwieldy structures to light weight structures on one hand and integration of varied properties on other hand to meet the application demands. In the present investigation an attempt is made to familiarize and best possibilities of reinforcing agent in aluminum 7075 matrix with naturally occurring beryl (Be) and graphene (Gr) to develop a new hybrid composite material. A stir casting process was used to fabricate with fixed volume fraction of 6wt% weight beryl and various volume fractions of 0.5wt%, 1wt%, 1.5wt% and 2wt% of graphene. The properties such as tensile strength, hardness and dry sliding wear behavior of hybrid composites were examined. The crystallite size and morphology of the graphene and beryl particles were analyzed with X-ray diffraction (XRD) and scanning electron microscopy (SEM) respectively. It was observed that ultimate tensile strength and hardness of the hybrid composite increased with increasing reinforcement volume fraction as compared to specimen without reinforcement additions. The dry sliding wear behavior of the hybrid composites decreases as compared to Al7075 alloy without reinforcement.

Keywords: Al7075, beryl, graphene, TEM, wear

Procedia PDF Downloads 137